In this article we will discuss a self-organizing map neural network for distinguishing salt-contaminated velocities from sediment-only velocities. Our objective is to demonstrate the capability of the self-organizing mapping neural network in automatic classification of salt-contaminated velocities as a replacement for interpreter's picking. The classified salt-contaminated velocities are then used to build a velocity model for subsalt imaging. We will illustrate our work with a Gulf of Mexico data set.

Subsalt imaging is in demand for hydrocarbon exploration in the Gulf of Mexico where subsurface salt covers a large portion of the deepwater region. Because of a large velocity contrast...

You do not currently have access to this article.